The area under the receiver operating characteristic curve (AUROC) of the test set is used throughout machine learning (ML) for assessing a model’s performance. However, when concordance is not the only ambition, this gives only a partial insight into performance, masking distribution shifts of model outputs and model instability.

中文翻译：

---

测试集 AUROC 的奇怪案例

测试集的受试者工作特征曲线 (AUROC) 下的面积在整个机器学习 (ML) 中用于评估模型的性能。然而，当一致性不是唯一的目标时，这只能提供对性能的部分了解，掩盖了模型输出的分布变化和模型的不稳定性。